Back to skill

Security audit

retire_age

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small China retirement-age calculator with no evidence of hidden access, persistence, data collection, or unsafe execution.

Before installing, users should understand this is a China-specific retirement-policy calculator with Chinese-only inputs and output. It requires uv and may prompt to install uv via Homebrew, but the reviewed script only performs local calculations from the values the user provides.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language description, parameter values, and policy text are all specified only in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to Chinese-language use. The policy allows locale constraints when clearly documented and justified, but this file does not explicitly state such a constraint or provide opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This code restricts accepted role inputs to Chinese literals only, and the command-line interface text is also Chinese-only. That creates a locale-specific constraint without user opt-in or a documented justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The parser description, help text, and choice labels are presented only in Chinese, which effectively forces a specific language experience. Because the file does not document that the skill is region-specific or provide a language choice, this is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest says the skill computes retirement time from a user's position information, gender, and birth date. However, the inline CLI help labels --role as 职位类型 while the accepted values are 男性, 女职工, and 女干部, which are gender/employment-category classes rather than general job positions. This is a documentation-level contradiction about what input the code expects.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.